{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IH7WUNTUIVQWGOTD3L5UBF4C33","short_pith_number":"pith:IH7WUNTU","canonical_record":{"source":{"id":"2606.11104","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T17:02:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c783e2f7b0f682d5fb7c02de58af77e21aa3556bfeaf164011483a5b70b14f03","abstract_canon_sha256":"6f1dd8b05cd33e3b3af3877aa646a1ce87d7e1ad7dc98129838abc6695cf30a6"},"schema_version":"1.0"},"canonical_sha256":"41ff6a36744561633a63dafb409782defbc89f2348e972784079c615df53f8dd","source":{"kind":"arxiv","id":"2606.11104","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11104","created_at":"2026-06-10T01:11:10Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11104v1","created_at":"2026-06-10T01:11:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11104","created_at":"2026-06-10T01:11:10Z"},{"alias_kind":"pith_short_12","alias_value":"IH7WUNTUIVQW","created_at":"2026-06-10T01:11:10Z"},{"alias_kind":"pith_short_16","alias_value":"IH7WUNTUIVQWGOTD","created_at":"2026-06-10T01:11:10Z"},{"alias_kind":"pith_short_8","alias_value":"IH7WUNTU","created_at":"2026-06-10T01:11:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IH7WUNTUIVQWGOTD3L5UBF4C33","target":"record","payload":{"canonical_record":{"source":{"id":"2606.11104","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T17:02:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c783e2f7b0f682d5fb7c02de58af77e21aa3556bfeaf164011483a5b70b14f03","abstract_canon_sha256":"6f1dd8b05cd33e3b3af3877aa646a1ce87d7e1ad7dc98129838abc6695cf30a6"},"schema_version":"1.0"},"canonical_sha256":"41ff6a36744561633a63dafb409782defbc89f2348e972784079c615df53f8dd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:11:10.466991Z","signature_b64":"DOUE4lEzEO9Wbeg1+/p12r41GFloSgNFlwDud2aH6/kOiZL351EZJR/fKWeiLmvcBplD7q6jJ/4DpBU89XDLBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41ff6a36744561633a63dafb409782defbc89f2348e972784079c615df53f8dd","last_reissued_at":"2026-06-10T01:11:10.466512Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:11:10.466512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.11104","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-10T01:11:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zuUGDLZP8DhB39R2Z6B//FnXHhhMx2bsP3KoUCtP/XFX0hEMyAw8BJ1QG/QfnmiZwDeInuoGqiXTgywX/o2JBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-22T06:21:59.568576Z"},"content_sha256":"fcded28cdfbf0c0b436766aadecfe5f3a659642ecfec5f6cd30ba16dd07fcc40","schema_version":"1.0","event_id":"sha256:fcded28cdfbf0c0b436766aadecfe5f3a659642ecfec5f6cd30ba16dd07fcc40"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IH7WUNTUIVQWGOTD3L5UBF4C33","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Limitations of Learning Tanh Neural Networks with Finite Precision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mat\\v{e}j Tr\\\"odler, Philipp Grohs","submitted_at":"2026-06-09T17:02:27Z","abstract_excerpt":"We investigate limitations of learning $\\tanh$ neural networks from point evaluations under finite-precision computations and $L^p$ accuracy guarantees, building on Berner, Grohs, and Voigtl\\\"ander (2023). Our approach is based on a novel construction of sharply localized bump functions via iterated $\\tanh$ activations. Using this mechanism, we show that, in a finite-precision setting, no adaptive randomized algorithm based on $m$ samples can achieve a convergence rate higher than the Monte Carlo rate $O(m^{-1/p})$ in the $L^p$ norm, unless the sampling budget grows exponentially with the size"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11104","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.11104/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-10T01:11:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lodvd5328CfL4OaujpMUzMzOQ7IDryDqZ/5Apzapk/Bnl4gEksY/rDOGvXFGSg2z6M+dcAj+mEnCCk53W+qoAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-22T06:21:59.568989Z"},"content_sha256":"d01e2251738043d9efedf2958249ba43f485c48b18292a8c6d5bc9dd0514b953","schema_version":"1.0","event_id":"sha256:d01e2251738043d9efedf2958249ba43f485c48b18292a8c6d5bc9dd0514b953"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IH7WUNTUIVQWGOTD3L5UBF4C33/bundle.json","state_url":"https://pith.science/pith/IH7WUNTUIVQWGOTD3L5UBF4C33/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IH7WUNTUIVQWGOTD3L5UBF4C33/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-22T06:21:59Z","links":{"resolver":"https://pith.science/pith/IH7WUNTUIVQWGOTD3L5UBF4C33","bundle":"https://pith.science/pith/IH7WUNTUIVQWGOTD3L5UBF4C33/bundle.json","state":"https://pith.science/pith/IH7WUNTUIVQWGOTD3L5UBF4C33/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IH7WUNTUIVQWGOTD3L5UBF4C33/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IH7WUNTUIVQWGOTD3L5UBF4C33","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6f1dd8b05cd33e3b3af3877aa646a1ce87d7e1ad7dc98129838abc6695cf30a6","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T17:02:27Z","title_canon_sha256":"c783e2f7b0f682d5fb7c02de58af77e21aa3556bfeaf164011483a5b70b14f03"},"schema_version":"1.0","source":{"id":"2606.11104","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11104","created_at":"2026-06-10T01:11:10Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11104v1","created_at":"2026-06-10T01:11:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11104","created_at":"2026-06-10T01:11:10Z"},{"alias_kind":"pith_short_12","alias_value":"IH7WUNTUIVQW","created_at":"2026-06-10T01:11:10Z"},{"alias_kind":"pith_short_16","alias_value":"IH7WUNTUIVQWGOTD","created_at":"2026-06-10T01:11:10Z"},{"alias_kind":"pith_short_8","alias_value":"IH7WUNTU","created_at":"2026-06-10T01:11:10Z"}],"graph_snapshots":[{"event_id":"sha256:d01e2251738043d9efedf2958249ba43f485c48b18292a8c6d5bc9dd0514b953","target":"graph","created_at":"2026-06-10T01:11:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.11104/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate limitations of learning $\\tanh$ neural networks from point evaluations under finite-precision computations and $L^p$ accuracy guarantees, building on Berner, Grohs, and Voigtl\\\"ander (2023). Our approach is based on a novel construction of sharply localized bump functions via iterated $\\tanh$ activations. Using this mechanism, we show that, in a finite-precision setting, no adaptive randomized algorithm based on $m$ samples can achieve a convergence rate higher than the Monte Carlo rate $O(m^{-1/p})$ in the $L^p$ norm, unless the sampling budget grows exponentially with the size","authors_text":"Mat\\v{e}j Tr\\\"odler, Philipp Grohs","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T17:02:27Z","title":"Limitations of Learning Tanh Neural Networks with Finite Precision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11104","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fcded28cdfbf0c0b436766aadecfe5f3a659642ecfec5f6cd30ba16dd07fcc40","target":"record","created_at":"2026-06-10T01:11:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6f1dd8b05cd33e3b3af3877aa646a1ce87d7e1ad7dc98129838abc6695cf30a6","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T17:02:27Z","title_canon_sha256":"c783e2f7b0f682d5fb7c02de58af77e21aa3556bfeaf164011483a5b70b14f03"},"schema_version":"1.0","source":{"id":"2606.11104","kind":"arxiv","version":1}},"canonical_sha256":"41ff6a36744561633a63dafb409782defbc89f2348e972784079c615df53f8dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41ff6a36744561633a63dafb409782defbc89f2348e972784079c615df53f8dd","first_computed_at":"2026-06-10T01:11:10.466512Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:11:10.466512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DOUE4lEzEO9Wbeg1+/p12r41GFloSgNFlwDud2aH6/kOiZL351EZJR/fKWeiLmvcBplD7q6jJ/4DpBU89XDLBw==","signature_status":"signed_v1","signed_at":"2026-06-10T01:11:10.466991Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.11104","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fcded28cdfbf0c0b436766aadecfe5f3a659642ecfec5f6cd30ba16dd07fcc40","sha256:d01e2251738043d9efedf2958249ba43f485c48b18292a8c6d5bc9dd0514b953"],"state_sha256":"7d4ac7786a42053bb026069b41e10adb05cbc53ec27c851bf3b39c2c76b24824"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wIHdxMZ1jzPXgu+Q9NhedTIwW2Dq7MlLMOlRDYXI1QfV5YnWcfXB+0Psj7Kuid9e9rbpk4I8BDjM/cGAIOFBAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-22T06:21:59.571348Z","bundle_sha256":"a24fa1647cc2b5d5f82461b1cf5dfffadca613987c8096aecd6fd8ca4eed4dcf"}}